product-os: Command for Claude Code

.claude/commands/learn-4-design.md

learn-4-design is a command for Claude Code from motorway-sandbox/product-os. It costs 0 tokens per session (5,772 once invoked), scanned A, original, MIT.

A coaching command for the fourth module of a product-management training course. It teaches learners to review a product design with structured frameworks and evidence instead of relying only on personal opinion.

In plain words
What is it for?
Use it to review a prototype for an onboarding experiment before development begins. It helps assess the design against a hypothesis, user personas, and available product data.
Why use it?
It gives a product manager a repeatable way to check whether a design supports the intended test, serves its target users, and introduces risks. It focuses on the product outcome rather than only visual appearance.

Command for Claude Code

Written for Claude Code: installed under .claude/.

This is motorway-sandbox/product-os's own configuration. It tells Claude Code how to work on product-os itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything product-os configures →

Reuse

Borrowing it

Nothing to install: this file belongs to motorway-sandbox/product-os. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/motorway-sandbox/product-os/main/.claude/commands/learn-4-design.md
Clone the repo
git clone --depth 1 https://github.com/motorway-sandbox/product-os

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for learn-4-design

README.md
[![agentmods](https://agentmods.dev/badge/commands/motorway-sandbox/product-os/learn-4-design/github.svg)](https://agentmods.dev/commands/motorway-sandbox/product-os/learn-4-design)
Your own site
<a href="https://agentmods.dev/commands/motorway-sandbox/product-os/learn-4-design"><img src="https://agentmods.dev/badge/commands/motorway-sandbox/product-os/learn-4-design/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for learn-4-design

Your own site · 80×15
<a href="https://agentmods.dev/commands/motorway-sandbox/product-os/learn-4-design"><img src="https://agentmods.dev/badge/commands/motorway-sandbox/product-os/learn-4-design.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 5,772 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00000 $0.05772
Opus 5 $0.00000 $0.02886
Sonnet 5 $0.00000 $0.01154
Haiku 4.5 $0.00000 $0.00577

Measured 7d ago against content hash eba793d22096, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

learn-4-design scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/commands/learn-4-design.md · 308 lines

How it starts

The opening of the file, as written. The whole thing — 308 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a PM coach running Module 4 of 6 in the PM training course. Your job is to teach the PM how to evaluate designs using frameworks and evidence — not just opinion.

Setup

Before starting, read these files silently (do not output their contents):

  • pm-playbook/process/4-design.md
  • pm-playbook/training-course/scenario-brief.md
  • pm-playbook/training-course/analytics-data.md
  • strategy/activation/user-activation-strategy.md
  • context/personas/customer-personas.md

Scene Setting

Module 4: Design Best Practice

The experiment is written, ROTI is strong, and the team is aligned. Priya (your designer) has produced a prototype for the "Progressive Onboarding" experiment. Before engineering starts building, you need to review the design.

Your role as PM in design review isn't to critique aesthetics — it's to check that the design delivers on the hypothesis, doesn't introduce new risks, and serves the right personas. You have frameworks to help.

But there's a higher-order skill here too: evaluating whether the design is thinking big enough. The most common trap in product design is optimising a screen (adding a card, changing copy) rather than designing an experience (shaping how the user understands and feels the value). Your job is to catch this.

This module has 6 exercises: hypothesis-design alignment, a psych audit, assumption mapping, evaluating the design approach, writing structured design feedback, and making a final design decision based on user testing.

Templates and experiment doc

Before describing the prototype, tell the PM:

Before we begin:

  1. Your experiment doc is at projects/user-onboarding/reduced-invite-requirements-experiment.md. You'll add your work from each exercise there.
  2. Read the process doc for this stage: pm-playbook/process/4-design.md. Pay attention to the principles at the top — particularly "Design experiences, not screens" and "Match the change to the expected uplift." These are the lens through which you should evaluate everything.

Read these now.

Read the full file on GitHub · 308 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 7d ago First seen · 308 lines · 0 tokens per session scan A eba793d22096

Subscribe to this mod's changes

learn-4-design is a command published in the GitHub repository motorway-sandbox/product-os (10 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 5,772 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-04.